使用2.2.T31-800I-A2-py311-openeuler24.03-lts-arm64 部署 DeepSeek-V3.2-Exp-W8A8时 失败。
启动时似乎报:
File "/usr/local/Ascend/atb-models/atb_llm/utils/mapping.py", line 532, in get_tp_group
module.num_group = self.world_size // module.group_size
~~~~~~~~~~~~~~~~^^~~~~~~~~~~~~~~~~~~
ZeroDivisionError: integer division or modulo by zero
和 [Errno 2] No such file or directory: '//16399_0_execute_request' 的错误,详细如下,请问具体是什么原因,有人用 mindie 2.2.T31 版本部署成功过 DeepSeek-V3.2吗?
[2025-11-21 19:54:14,407] [16446] [281471352762080] [llm] [INFO] [request_router.py-69] : init base config
[2025-11-21 19:54:14,407] [16446] [281471352762080] [llm] [INFO] [metrics.py-56] : profiling is disenabled.
[2025-11-21 19:54:28,300] [16437] [281471820099296] [llmmodels] [INFO] [model_runner.py-160] : model_runner.quantize: w8a8, model_runner.kv_quant_type: None, model_runner.fa_quant_type: None, model_runner.dtype: torch.bfloat16
Traceback (most recent call last):
File "/usr/local/lib/python3.11/site-packages/mindie_llm/connector/request_router/request_router.py", line 23, in run
self._target(*self._args, **self._kwargs)
File "/usr/local/lib/python3.11/site-packages/mindie_llm/connector/request_router/request_router.py", line 99, in do_inference
self.initialize(execute_request.config)
File "/usr/local/lib/python3.11/site-packages/mindie_llm/connector/request_router/request_router.py", line 84, in initialize
initialize_result = self.router_impl.initialize(config)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/usr/local/lib/python3.11/site-packages/mindie_llm/connector/request_router/router_impl.py", line 166, in initialize
self.generator = Generator(model_config={**model_config.model_config})
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/usr/local/lib/python3.11/site-packages/mindie_llm/text_generator/generator.py", line 204, in __init__
self.generator_backend = get_generator_backend(model_config)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/usr/local/lib/python3.11/site-packages/mindie_llm/text_generator/adapter/__init__.py", line 32, in get_generator_backend
return generator_cls(model_config)
^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/usr/local/lib/python3.11/site-packages/mindie_llm/text_generator/adapter/generator_torch.py", line 134, in __init__
super().__init__(model_config)
File "/usr/local/lib/python3.11/site-packages/mindie_llm/text_generator/adapter/generator_backend.py", line 152, in __init__
self.model_wrapper = get_model_wrapper(model_config, backend_type)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/usr/local/lib/python3.11/site-packages/mindie_llm/modeling/model_wrapper/__init__.py", line 15, in get_model_wrapper
return wrapper_cls(**model_config)
^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/usr/local/lib/python3.11/site-packages/mindie_llm/modeling/model_wrapper/atb/atb_model_wrapper.py", line 35, in __init__
self.model_runner = ModelRunner(
^^^^^^^^^^^^
File "/usr/local/Ascend/atb-models/atb_llm/runner/model_runner.py", line 185, in __init__
self.mapping = Mapping(world_size=world_size, rank=rank, llm_config=self.llm_config, **kwargs)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/usr/local/Ascend/atb-models/atb_llm/utils/mapping.py", line 133, in __init__
self.get_tp_group(self.moe_ep_intra_node)
File "/usr/local/Ascend/atb-models/atb_llm/utils/mapping.py", line 532, in get_tp_group
module.num_group = self.world_size // module.group_size
~~~~~~~~~~~~~~~~^^~~~~~~~~~~~~~~~~~~
ZeroDivisionError: integer division or modulo by zero
/usr/lib64/python3.11/multiprocessing/resource_tracker.py:254: UserWarning: resource_tracker: There appear to be 6 leaked shared_memory objects to clean up at shutdown
warnings.warn('resource_tracker: There appear to be %d '
/usr/lib64/python3.11/multiprocessing/resource_tracker.py:267: UserWarning: resource_tracker: '//16399_0_execute_request': [Errno 2] No such file or directory: '//16399_0_execute_request'
warnings.warn('resource_tracker: %r: %s' % (name, e))
/usr/lib64/python3.11/multiprocessing/resource_tracker.py:267: UserWarning: resource_tracker: '//16399_0_shared_sync_link_response': [Errno 2] No such file or directory: '//16399_0_shared_sync_link_response'
warnings.warn('resource_tracker: %r: %s' % (name, e))
/usr/lib64/python3.11/multiprocessing/resource_tracker.py:267: UserWarning: resource_tracker: '//16399_0_transfer_response': [Errno 2] No such file or directory: '//16399_0_transfer_response'
warnings.warn('resource_tracker: %r: %s' % (name, e))
/usr/lib64/python3.11/multiprocessing/resource_tracker.py:267: UserWarning: resource_tracker: '//16399_0_shared_sync_link_request': [Errno 2] No such file or directory: '//16399_0_shared_sync_link_request'
warnings.warn('resource_tracker: %r: %s' % (name, e))
/usr/lib64/python3.11/multiprocessing/resource_tracker.py:267: UserWarning: resource_tracker: '//16399_0_transfer_request': [Errno 2] No such file or directory: '//16399_0_transfer_request'
warnings.warn('resource_tracker: %r: %s' % (name, e))
/usr/lib64/python3.11/multiprocessing/resource_tracker.py:267: UserWarning: resource_tracker: '//16399_0_execute_response': [Errno 2] No such file or directory: '//16399_0_execute_response'
warnings.warn('resource_tracker: %r: %s' % (name, e))
Daemon is killing...
All subprocesses exited gracefully.
启动时似乎报:
File "/usr/local/Ascend/atb-models/atb_llm/utils/mapping.py", line 532, in get_tp_group
module.num_group = self.world_size // module.group_size
~~~~~~~~~~~~~~~~^^~~~~~~~~~~~~~~~~~~
ZeroDivisionError: integer division or modulo by zero
和 [Errno 2] No such file or directory: '//16399_0_execute_request' 的错误,详细如下,请问具体是什么原因,有人用 mindie 2.2.T31 版本部署成功过 DeepSeek-V3.2吗?
[2025-11-21 19:54:14,407] [16446] [281471352762080] [llm] [INFO] [request_router.py-69] : init base config
[2025-11-21 19:54:14,407] [16446] [281471352762080] [llm] [INFO] [metrics.py-56] : profiling is disenabled.
[2025-11-21 19:54:28,300] [16437] [281471820099296] [llmmodels] [INFO] [model_runner.py-160] : model_runner.quantize: w8a8, model_runner.kv_quant_type: None, model_runner.fa_quant_type: None, model_runner.dtype: torch.bfloat16
Traceback (most recent call last):
File "/usr/local/lib/python3.11/site-packages/mindie_llm/connector/request_router/request_router.py", line 23, in run
self._target(*self._args, **self._kwargs)
File "/usr/local/lib/python3.11/site-packages/mindie_llm/connector/request_router/request_router.py", line 99, in do_inference
self.initialize(execute_request.config)
File "/usr/local/lib/python3.11/site-packages/mindie_llm/connector/request_router/request_router.py", line 84, in initialize
initialize_result = self.router_impl.initialize(config)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/usr/local/lib/python3.11/site-packages/mindie_llm/connector/request_router/router_impl.py", line 166, in initialize
self.generator = Generator(model_config={**model_config.model_config})
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/usr/local/lib/python3.11/site-packages/mindie_llm/text_generator/generator.py", line 204, in __init__
self.generator_backend = get_generator_backend(model_config)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/usr/local/lib/python3.11/site-packages/mindie_llm/text_generator/adapter/__init__.py", line 32, in get_generator_backend
return generator_cls(model_config)
^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/usr/local/lib/python3.11/site-packages/mindie_llm/text_generator/adapter/generator_torch.py", line 134, in __init__
super().__init__(model_config)
File "/usr/local/lib/python3.11/site-packages/mindie_llm/text_generator/adapter/generator_backend.py", line 152, in __init__
self.model_wrapper = get_model_wrapper(model_config, backend_type)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/usr/local/lib/python3.11/site-packages/mindie_llm/modeling/model_wrapper/__init__.py", line 15, in get_model_wrapper
return wrapper_cls(**model_config)
^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/usr/local/lib/python3.11/site-packages/mindie_llm/modeling/model_wrapper/atb/atb_model_wrapper.py", line 35, in __init__
self.model_runner = ModelRunner(
^^^^^^^^^^^^
File "/usr/local/Ascend/atb-models/atb_llm/runner/model_runner.py", line 185, in __init__
self.mapping = Mapping(world_size=world_size, rank=rank, llm_config=self.llm_config, **kwargs)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/usr/local/Ascend/atb-models/atb_llm/utils/mapping.py", line 133, in __init__
self.get_tp_group(self.moe_ep_intra_node)
File "/usr/local/Ascend/atb-models/atb_llm/utils/mapping.py", line 532, in get_tp_group
module.num_group = self.world_size // module.group_size
~~~~~~~~~~~~~~~~^^~~~~~~~~~~~~~~~~~~
ZeroDivisionError: integer division or modulo by zero
/usr/lib64/python3.11/multiprocessing/resource_tracker.py:254: UserWarning: resource_tracker: There appear to be 6 leaked shared_memory objects to clean up at shutdown
warnings.warn('resource_tracker: There appear to be %d '
/usr/lib64/python3.11/multiprocessing/resource_tracker.py:267: UserWarning: resource_tracker: '//16399_0_execute_request': [Errno 2] No such file or directory: '//16399_0_execute_request'
warnings.warn('resource_tracker: %r: %s' % (name, e))
/usr/lib64/python3.11/multiprocessing/resource_tracker.py:267: UserWarning: resource_tracker: '//16399_0_shared_sync_link_response': [Errno 2] No such file or directory: '//16399_0_shared_sync_link_response'
warnings.warn('resource_tracker: %r: %s' % (name, e))
/usr/lib64/python3.11/multiprocessing/resource_tracker.py:267: UserWarning: resource_tracker: '//16399_0_transfer_response': [Errno 2] No such file or directory: '//16399_0_transfer_response'
warnings.warn('resource_tracker: %r: %s' % (name, e))
/usr/lib64/python3.11/multiprocessing/resource_tracker.py:267: UserWarning: resource_tracker: '//16399_0_shared_sync_link_request': [Errno 2] No such file or directory: '//16399_0_shared_sync_link_request'
warnings.warn('resource_tracker: %r: %s' % (name, e))
/usr/lib64/python3.11/multiprocessing/resource_tracker.py:267: UserWarning: resource_tracker: '//16399_0_transfer_request': [Errno 2] No such file or directory: '//16399_0_transfer_request'
warnings.warn('resource_tracker: %r: %s' % (name, e))
/usr/lib64/python3.11/multiprocessing/resource_tracker.py:267: UserWarning: resource_tracker: '//16399_0_execute_response': [Errno 2] No such file or directory: '//16399_0_execute_response'
warnings.warn('resource_tracker: %r: %s' % (name, e))
Daemon is killing...
All subprocesses exited gracefully.